logo-image-design
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection because it ingests untrusted user input and interpolates it into structured data artifacts including CSV, SQL, and JSON Schema.
- Ingestion points: The skill captures business names, taglines, and descriptions of business activities directly from user messages (Step 1 and Step 2 in
SKILL.md). - Boundary markers: The instructions do not specify the use of delimiters or explicit boundary markers when interpolating this user data into the generated templates.
- Capability inventory: The agent is instructed to generate machine-readable artifacts such as CSV, PostgreSQL DDL (
CREATE TABLEstatements), and JSON objects based on the collected context (Step 5 inSKILL.md). - Sanitization: There are no specific instructions for sanitizing, escaping, or validating the user-provided strings before they are placed into SQL queries or CSV rows, which could allow a malicious user to supply strings designed to break the formatting or perform schema confusion.
Audit Metadata